Govern the skill inventory by evaluating, scoring, tagging, and normalizing every Skill in the repository (including this one). Produce a single source of truth: machine-readable scores and status per skill, normalized human-facing README, overlap detection, and a repo-level summary. Agent-first; README for humans, agent.yaml for Agents.
Interaction: Before overwriting many skill files or writing ASQMAUDIT.md, confirm with the user unless they have explicitly requested a full run (e.g. “curate all skills” or “run curate-skills”).
When this skill writes or updates a skill’s agent.yaml, it uses this structure so Agents can consume it without reading README:
Valutare, assegnare un punteggio (ASQM rigoroso), etichettare e normalizzare tutte le abilità; scrive agent.yaml e README per competenza, rileva sovrapposizioni, produce ASQM_AUDIT.md o riepilogo della chat. Da utilizzare durante il controllo delle competenze, dopo aver aggiunto/modificato le competenze o quando si generano riepiloghi delle competenze a livello di repository. Fonte: nesnilnehc/ai-cortex.